AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Intelli-Paint: Towards Developing More Human-Intelligible Painting Agents

Jaskirat Singh, Cameron Smith, Jose Echevarria, Liang Zheng

ECCV 2022 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Intelli-Paint instead of Paint Transformerpainting agent · CUB-Birds (~300 strokes)L_pixel: 82.43 -> 50.94Improved
use Intelli-Paint instead of RLpainting agent · CUB-Birds (~300 strokes)L_pixel: 72.93 -> 50.94Improved
use Intelli-Paint instead of Optimpainting agent · Stanford Cars (~300 strokes)L_pixel: 76.52 -> 56.92Improved
use Intelli-Paint instead of Semantic-RLpainting agent · Stanford Cars (~300 strokes)L_pcpt: 0.55 -> 0.44Improved
Paint Transformer vs Optim under small stroke budgetPaint Transformer · Stanford Cars (~300 strokes)L_pixel: 76.52 -> 87.78Hurt
add progressive layering, sequential guidance and stroke regularizationpainting agent · human-likeness user study Bpreference %: 69.09% to 86.50% preferring Intelli-PaintImproved
provide human reference sequence in the studyuser study · User Study A vs Bpreference %: 83.11 -> 87.17 (RL)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy